Hugging Face's logo

fieldvalley-llm2025
/
main_rev1_merged_dpo05

Text Generation
Transformers
Safetensors
qwen3
dpo
unsloth
qwen
toml
conversational
text-generation-inference
Model card Files
xet
 Community

fieldvalley-llm2025/main_rev1_merged_dpo05

REV1 DPO05 (Fixed Steps Version).

  • Base: REV1 DPO03
  • Method: TOML Local DPO
  • Steps: 100 (Fixed)
  • Pairs: Increased with multi-type rejection
Downloads last month
2
Safetensors
Model size
4B params
Tensor type
F16
·
Inference Providers NEW
Text Generation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fieldvalley-llm2025/main_rev1_merged_dpo05

Base model

Qwen/Qwen2.5-7B
Finetuned
Qwen/Qwen2.5-7B-Instruct
Finetuned
fieldvalley-llm2025/llm2025_main_merged_dpo03
Finetuned
(3)
this model